arXiv AI
Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 8
MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration
arXiv:2610.10457v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) achieve remarkable performance in video synthesis, but their iterative denoising process suffers from high inference late...
arXiv Machine Learning
Sep 22
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
arXiv:2602.24208v2 Announce Type: replace-cross Abstract: Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequenti...
arXiv Machine Learning
Aug 3
OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
arXiv AI
Sep 25
Accelerating Video Diffusion via Training-Free Trajectory Routing
The paper introduces TRACK, a training‑free trajectory routing method that accelerates video diffusion by selectively switching between large and small models during denoising steps. A calibration process generates a disagreement score map, guiding the selection of the appropriate model at each step to maintain quality while reducing computational cost. Experiments on Wan 2.1, Cosmos 3, TurboDiffusion, and FastVideo show speedups ranging from 1.95× to 2.73× with comparable quality and diversity.
arXiv Computer Vision
Sep 30
RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance
arXiv:2609.36433v1 Announce Type: new Abstract: Diffusion models enable high-quality visual generation, but iterative denoising remains computationally expensive, especially under classifier-free gui...
arXiv AI
Aug 14
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
arXiv:2608. 13043v1 Announce Type: new Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead.